Pruna AI P-Video Replace is a fast AI video subject replacement model that replaces or inserts reference subjects into a source video while preserving the original motion, timing, and optional audio. Ready-to-use REST inference API for video subject replacement, character insertion, product placement, creative video editing, advertising creatives, social media content, and professional video editing workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.03per run·~33 / $1
Pruna AI P-Video Replace replaces or inserts a reference subject into a source video while preserving the original motion. Upload one source video, add one to three reference images, and use a prompt to describe how the subject should appear in the final result. It is suitable for character replacement, identity transfer, stylized casting swaps, and other motion-preserving video editing workflows.
Reference-guided subject replacement
Use one to three reference images to replace or insert a person or subject into an existing video.
Motion-preserving editing
Keep the motion from the source video while changing who appears in the scene.
Simple replacement workflow
Upload a video, add reference images, describe the replacement, and generate the edited result.
Flexible output settings
Choose 720p or 1080p, select frame rate behavior, and optionally keep the output audio.
Production-ready API
Useful for creator workflows, identity transfer, stylized edits, promo content, and fast concept testing.
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video URL. |
| images | Yes | Reference image URLs for replacement. Supports 1 to 3 images. |
| prompt | No | Instruction describing how the reference image should be placed into the video. Default: Place the reference person into the video while preserving the original motion. |
| resolution | No | Output video resolution. Supported values: 720p, 1080p. Default: 720p. |
| fps | No | Target output frame rate. Supported values: original, 24, 48. Default: original. |
| save_audio | No | Save the output video with audio. Default: true. |
1 to 3 images of the person or subject you want to insert or replace.720p for lower cost or 1080p for higher quality.24 or 48.save_audio=true if you want the output video to include audio.Place the reference person into the video while preserving the original motion, body rhythm, and scene timing. Keep the result natural and consistent with the original lighting.
Pricing depends on source video duration and resolution.
video duration720p costs $0.03 per billed second1080p costs $0.06 per billed secondimages, prompt, fps, and save_audio do not affect pricing| Resolution | 1s | 5s | 10s | 20s |
|---|---|---|---|---|
| 720p | $0.03 | $0.15 | $0.30 | $0.60 |
| 1080p | $0.06 | $0.30 | $0.60 | $1.20 |
720p for quick testing and 1080p for higher-quality final outputs.video and images are required.images supports 1 to 3 reference images.save_audio controls whether the output video includes audio, but does not affect pricing.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for P Video Replace below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"resolution": "720p",
"fps": "original",
"save_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"resolution": "720p",
"fps": "original",
"save_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"resolution": "720p",
"fps": "original",
"save_audio": True
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)P Video Replace is a Pruna Ai model for AI inference, exposed as a REST API on WaveSpeedAI. Pruna AI P-Video Replace is a fast AI video subject replacement model that replaces or inserts reference subjects into a source video while preserving the original motion, timing, and optional audio. Ready-to-use REST inference API for video subject replacement, character insertion, product placement, creative video editing, advertising creatives, social media content, and professional video editing workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-video-replace.
P Video Replace starts at $0.030 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `video`, `resolution`, `fps`, `save_audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-video-replace.
Median end-to-end generation time on WaveSpeedAI is around 68 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Pruna Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.